CN108491785A - A kind of artificial intelligence image identification attack defending system - Google Patents
A kind of artificial intelligence image identification attack defending system Download PDFInfo
- Publication number
- CN108491785A CN108491785A CN201810223172.3A CN201810223172A CN108491785A CN 108491785 A CN108491785 A CN 108491785A CN 201810223172 A CN201810223172 A CN 201810223172A CN 108491785 A CN108491785 A CN 108491785A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- artificial intelligence
- coding
- server end
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/96—Management of image or video recognition tasks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/40—Spoof detection, e.g. liveness detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
- H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/12—Applying verification of the received information
- H04L63/123—Applying verification of the received information received data contents, e.g. message integrity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/06—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols the encryption apparatus using shift registers or memories for block-wise or stream coding, e.g. DES systems or RC4; Hash functions; Pseudorandom sequence generators
- H04L9/0643—Hash functions, e.g. MD5, SHA, HMAC or f9 MAC
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Power Engineering (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of artificial intelligence image identification attack defending system, the system comprises:Monitor end and server end, the monitor end and the server end are communicatively coupled;The monitor end includes that image object position detecting module, picture number value module, safety of image coding module and coding transmission encrypting module, the server end include coding transmission deciphering module, safety of image decoder module, numerical imaging module, two sorting algorithm module of image object, artificial intelligence deep learning server host and backstage image object database;The present invention carries out the intelligent recognition of face by artificial intelligence image identification attack defending system, and artificial intelligence pattern recognition is avoided to obscure attack, quickly judges the true or false of image object, improves the safety of recognition of face.
Description
Technical field
The present invention relates to artificial intelligence image identification technical field more particularly to a kind of attack of artificial intelligence image identification are anti-
Imperial system.
Background technology
Currently, AI(Artificial Intelligence, artificial intelligence are research, develop for simulating, extending and expand
Open up theory, the new technological sciences of method, technology and application system of the intelligence of people)Arrival will lead the mankind enter one
In a new epoch, with the development of computer technology and information technology, AI artificial intelligence more and more affects our day
Often life.
Image recognition refers to being handled image, analyzed and being understood using computer, to identify various different modes
Then target and technology to picture, general industry recycle software according to picture ash in use, shoot picture using industrial camera
Scale does further identifying processing.
Recognition of face at present has begun widespread adoption, but the work in terms of security protection is then weaker, especially
Image Acquisition front end(Camera), the case where security protection ability is especially weak, and camera is by invasion and abduction is very universal;Such as
Fruit attacker invades camera, distorts the image and video of camera acquisition, then it is artificial can to mislead the recognition of face on backstage etc.
Intelligent treatment.
Therefore, the existing technology needs to be improved and developed.
Invention content
The technical problem to be solved in the present invention is, for prior art defect, the present invention provides a kind of artificial intelligence figure
As identification attack defending system, it is intended to which the intelligent recognition for carrying out face by artificial intelligence image identification attack defending system is kept away
Attack is obscured in the identification of manpower-free's intelligent graphic, quickly judges the true or false of image object, improves the safety of recognition of face.
The technical proposal for solving the technical problem of the invention is as follows:
A kind of artificial intelligence image identification attack defending system, wherein the artificial intelligence image identification attack defending system packet
It includes:
Monitor end and server end, the monitor end and the server end are communicatively coupled;
The monitor end includes:
Image object position detecting module, the image for obtaining monitor in real time carry out target location identification, and extracting needs
Carry out the pixel of safe coding protection;
Picture number value module, for image to be digitized processing;
Safety of image coding module, the coding for the image after digitized processing to be carried out to security algorithm;
Coding transmission encrypting module is transmitted by network package into server end for being encrypted coding information;
The server end includes:
Coding transmission deciphering module, for decrypting the coding information received;
Safety of image decoder module, for the coding information after decryption to be solved the numerical value before original image encodes, and through number
Image algorithm is reduced into original target image;
Numerical imaging module, for numerical value to be carried out image conversion processing;
Two sorting algorithm module of image object, for by the artificially defined rule base of target genuine-fake feature, tentatively judging figure
As the true or false of target;
After the detail characteristic for comparing recognisable image target, characteristic information is passed for artificial intelligence deep learning server host
It send to backstage image object database;
Backstage image object database after the corresponding informance for comparing image target signature, is passed back or is shown according to application range
Show the truthful data information of image object.
The artificial intelligence image identification attack defending system, wherein the monitor end further includes:For carrying out shadow
As the monitor of capture.
The artificial intelligence image identification attack defending system, wherein the monitor includes that camera and movement are whole
End.
The artificial intelligence image identification attack defending system, wherein the coding transmission encrypting module passes through Hash
Coding information is encrypted algorithm.
The artificial intelligence image identification attack defending system, wherein the coding transmission deciphering module passes through Hash
The coding information received is decrypted in algorithm.
The artificial intelligence image identification attack defending system, wherein the server end further includes:
Face identifying data comparing module, for according to the truthful data information obtained by the backstage image object database
Obtain identification result.
The artificial intelligence image identification attack defending system, wherein the server end further includes:
Face characteristic picture searching module, for according to the truthful data information obtained by the backstage image object database
Obtain picture recognition result.
The artificial intelligence image identification attack defending system, wherein the server end further includes:
Image detection module is attacked for judging that image has been met with when transmitting package in two sorting algorithm module of described image target
Image is detected again when hitting.
The invention discloses a kind of artificial intelligence image identification attack defending system, the system comprises:Monitor end and
Server end, the monitor end and the server end are communicatively coupled;The monitor end includes image object position
Detection module, picture number value module, safety of image coding module and coding transmission encrypting module, the server end include
It is coding transmission deciphering module, safety of image decoder module, numerical imaging module, two sorting algorithm module of image object, artificial
Intelligent deep learning server host and backstage image object database;The present invention is attacked anti-by artificial intelligence image identification
Imperial system carries out the intelligent recognition of face, and artificial intelligence pattern recognition is avoided to obscure attack, quickly judges the true and false of image object
Property, improve the safety of recognition of face.
Description of the drawings
Fig. 1 is the schematic diagram of the function of the preferred embodiment of artificial intelligent image identification attack defending system of the invention.
Specific implementation mode
To make the objectives, technical solutions, and advantages of the present invention clearer and more explicit, develop simultaneously embodiment pair referring to the drawings
The present invention is further described.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and do not have to
It is of the invention in limiting.
To make the objectives, technical solutions, and advantages of the present invention clearer and more explicit, develop simultaneously embodiment pair referring to the drawings
The present invention is further described.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and do not have to
It is of the invention in limiting.
Artificial intelligence image identification attack defending system described in present pre-ferred embodiments, as shown in Figure 1, a kind of artificial
Intelligent image recognizes attack defending system, wherein the artificial intelligence image identification attack defending system includes:
Monitor end 100 and server end 200, the monitor end 100 and the server end 200 are communicatively coupled;Institute
Stating monitor end 100 includes:Image object position detecting module 110, the image for obtaining monitor in real time carry out target
Position identifies, extracts the pixel for needing to carry out safe coding protection;Picture number value module 120, for carrying out image
Digitized processing;Safety of image coding module 130, the coding for the image after digitized processing to be carried out to security algorithm;It compiles
Code transmission encrypting module 140 is transmitted by network package into server end for being encrypted coding information;The service
Device end 200 includes:Coding transmission deciphering module 210, for decrypting the coding information received;Safety of image decoder module
220, for the coding information after decryption to be solved to the numerical value before original image coding, and it is reduced into through digital picture algorithm original
Target image;Numerical imaging module 230, for numerical value to be carried out image conversion processing;Two sorting algorithm module of image object
240, for by the artificially defined rule base of target genuine-fake feature, tentatively judging the true or false of image object;Artificial intelligence
Characteristic information after the detail characteristic for comparing recognisable image target, is sent to backstage and schemed by deep learning server host 250
As target database;Backstage image object database 260, after the corresponding informance for comparing image target signature, according to application
The truthful data information of image object is passed or shown to range back.
Wherein, the present invention first carries out real time acquisition via watchdog hardware for image instantly, recycles image object position
It sets detection module 110 and carries out target identification(Not every pixel is required for carrying out safe coding, only key images part
It needs to carry out safe coding protection, it is therefore desirable to target identification is first carried out, the part for needing to carry out safe coding protection is extracted,
To reduce freight volume), and be digitized image using picture number value module 120, the image being digitized into, into figure
As safe coding module 130, after the coding for carrying out security algorithm, then by this coding information with coding transmission encrypting module 140 into
Row encryption, is finally transmitted through network package into server end 200.
Wherein, safety of image coding module 130 can carry out safe coding, by coding of graphics in each pixel position of image
Information is sent to backstage through picture number value module 120(It refer to the backstage handled image and video), by decoding from the background
For original image;After watchdog hardware obtains original image, target identification is carried out to the content of original image, in target image
While content is digitized processing, the security protection hardware of addition carries out safe coding, to prevent attacker from distorting figure
The content of picture.
Further, the monitor end 100 further includes:Monitor for carrying out image capture;The monitor packet
Include camera and mobile terminal.
Wherein, coding information is encrypted by hash algorithm for the coding transmission encrypting module 140;The coding passes
Defeated deciphering module 210 is decrypted the coding information received by hash algorithm.
Further, as shown in Figure 1, the server end 200 further includes:Face identifying data comparing module 270, is used for
According to the truthful data acquisition of information identification result obtained by the backstage image object database;Face characteristic picture
Search module 280, for according to the truthful data acquisition of information picture recognition obtained by the backstage image object database
As a result.
Further, as shown in Figure 1, the server end 200 further includes:Image detection module 290, in the figure
Image is detected again when judging that image has met with attack when transmitting package as two sorting algorithm module 240 of target.
Specifically, the present invention is carried out via watchdog hardware (or other image capturing devices) for image instantly real first
When capture, recycle image object position detecting module 110 to carry out target location identification, and utilize picture number value module 120
Image (such as this example is a face) is digitized, the image being digitized into, (such as into safety of image coding module 130
The present embodiment is a hash algorithm encrypting module), after the coding for carrying out security algorithm, then this coding information added with coding transmission
Close module 140 is encrypted, and is finally transmitted into server end 200 through network package.
Server end 200 then decrypts coding information first with coding transmission deciphering module 210, and by the coding of the decryption
Information solves numerical value before original image coding, is most gone back afterwards through digital picture module 230 through safety of image decoder module 220
Original is at original target image.
In general, carrying out artificial intelligence pattern recognition obscures attack, (such as:Deep learning network differential evolution attack,
And forge false face recognition attack etc., differential evolution is a kind of optimization algorithm in artificial intelligence image recognition.Differential evolution
Attack is sent to the face picture pixel of server end for change local side, and the single pixel point or more pixels to face picture click through
Row modification, makes server end deep learning artificial intelligence (DNN) judge misalignment), the attack time point of hacker's most probable, exactly figure
Package gets forwarded to the process of 200 host of server end through network, i.e., is transmitted by the coding transmission encrypting module 140 at monitor end 100
To the process of the coding transmission deciphering module of server end 200.
The present invention obscures attack in order to avoid artificial intelligence pattern recognition, and artificial intelligence target identification server end is caused to meet with
The risk obscured before decrypted image enters artificial intelligence deep learning server, need to first pass through two sorting algorithm mould of image object
Block 240 tentatively judges the true or false of the image object with the artificially defined rule base of target genuine-fake feature(Due to camera etc.
The operational capability of image and video capture device is limited, can have error to the identification of the image block similar to face, not
It is that face but shape are similar to the image block of face and are labeled as target image, and carry out safe coding, in order to improve in next step
Recognition of face processing efficiency, need to sift out first be not face part;It means to by checking that safe coding finds target
After image has been tampered with, further analyze whether the target distorted is that plan carries out obscuring attack;Because in image data
In transmission process, it can also be not necessarily and targetedly attack there is a situation where data transmission fault).
Such as target really to meet the target signature of the artificially defined rule base of target genuine-fake feature, this figure just allow through
It is further compared by artificial intelligence deep learning network (DNN).It is such as unsatisfactory for, you can learn that this picture is possible to transmitting
It when package, suffers from hacker and carries out obscuring attack, not directly by this information input artificial intelligent recognition database, Yi Mianzao
Obscure at database, this picture need to be sent to image detection module 290 and checked again for.
Further after the detail characteristic of the comparison identification target, its feature is believed for artificial intelligence deep learning network (DNN)
Breath, is sent to 260 processing center of backstage target database, pair of the target signature is successfully compared through backstage target database 260
After answering information, according to application range, the truthful data information of this target is passed or shown back.
In conclusion the present invention provides a kind of artificial intelligence image identification attack defending system, the system comprises:Monitoring
Device end and server end, the monitor end and the server end are communicatively coupled;The monitor end includes image mesh
Cursor position detection module, picture number value module, safety of image coding module and coding transmission encrypting module, the server
End includes coding transmission deciphering module, safety of image decoder module, numerical imaging module, two sorting algorithm mould of image object
Block, artificial intelligence deep learning server host and backstage image object database;The monitor end will obtain in real time
Image carries out target location identification, obtains the pixel for needing to carry out safe coding protection, and image is digitized processing;
The monitor end encodes the image after digitized processing, and is passed by network package after coding information is encrypted
It is sent into the server end;The server end decrypts the coding information received, and is reduced into original target image, will count
After value carries out image conversion processing, the true or false of image object is tentatively judged;The server end comparison recognisable image target
Detail characteristic, and the corresponding informance of image target signature is compared, pass or show the true number of image object back according to application range
It is believed that breath.The present invention avoids artificial intelligence pattern recognition from obscuring attack, quickly judges image object by the intelligent recognition of face
True or false, improve the safety of recognition of face.
Certainly, one of ordinary skill in the art will appreciate that realizing all or part of flow in above-described embodiment method,
It is that can instruct related hardware by computer program(Such as processor, controller etc.)It completes, the program can store
In a computer-readable storage medium, described program may include the flow such as above-mentioned each method embodiment when being executed.
Wherein the storage medium can be memory, magnetic disc, CD etc..
It should be understood that the application of the present invention is not limited to the above for those of ordinary skills can
With improvement or transformation based on the above description, all these modifications and variations should all belong to the guarantor of appended claims of the present invention
Protect range.
Claims (8)
1. a kind of artificial intelligence image identification attack defending system, which is characterized in that the artificial intelligence image identification attack is anti-
Imperial system includes:
Monitor end and server end, the monitor end and the server end are communicatively coupled;
The monitor end includes:
Image object position detecting module, the image for obtaining monitor in real time carry out target location identification, and extracting needs
Carry out the pixel of safe coding protection;
Picture number value module, for image to be digitized processing;
Safety of image coding module, the coding for the image after digitized processing to be carried out to security algorithm;
Coding transmission encrypting module is transmitted by network package into server end for being encrypted coding information;
The server end includes:
Coding transmission deciphering module, for decrypting the coding information received;
Safety of image decoder module, for the coding information after decryption to be solved the numerical value before original image encodes, and through number
Image algorithm is reduced into original target image;
Numerical imaging module, for numerical value to be carried out image conversion processing;
Two sorting algorithm module of image object, for by the artificially defined rule base of target genuine-fake feature, tentatively judging figure
As the true or false of target;
After the detail characteristic for comparing recognisable image target, characteristic information is passed for artificial intelligence deep learning server host
It send to backstage image object database;
Backstage image object database after the corresponding informance for comparing image target signature, is passed back or is shown according to application range
Show the truthful data information of image object.
2. artificial intelligence image identification attack defending system according to claim 1, which is characterized in that the monitor end
Further include:Monitor for carrying out image capture.
3. artificial intelligence image identification attack defending system according to claim 2, which is characterized in that the monitor packet
Include camera and mobile terminal.
4. artificial intelligence image identification attack defending system according to claim 1, which is characterized in that the coding transmission
Coding information is encrypted by hash algorithm for encrypting module.
5. artificial intelligence image identification attack defending system according to claim 1, which is characterized in that the coding transmission
Deciphering module is decrypted the coding information received by hash algorithm.
6. artificial intelligence image identification attack defending system according to claim 1, which is characterized in that the server end
Further include:
Face identifying data comparing module, for according to the truthful data information obtained by the backstage image object database
Obtain identification result.
7. artificial intelligence image identification attack defending system according to claim 1, which is characterized in that the server end
Further include:
Face characteristic picture searching module, for according to the truthful data information obtained by the backstage image object database
Obtain picture recognition result.
8. artificial intelligence image identification attack defending system according to claim 1, which is characterized in that the server end
Further include:
Image detection module is attacked for judging that image has been met with when transmitting package in two sorting algorithm module of described image target
Image is detected again when hitting.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810223172.3A CN108491785B (en) | 2018-03-19 | 2018-03-19 | Artificial intelligence image identification attack defense system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810223172.3A CN108491785B (en) | 2018-03-19 | 2018-03-19 | Artificial intelligence image identification attack defense system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108491785A true CN108491785A (en) | 2018-09-04 |
CN108491785B CN108491785B (en) | 2020-07-28 |
Family
ID=63339904
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810223172.3A Active CN108491785B (en) | 2018-03-19 | 2018-03-19 | Artificial intelligence image identification attack defense system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108491785B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109271137A (en) * | 2018-09-11 | 2019-01-25 | 网御安全技术(深圳)有限公司 | A kind of modular multiplication device and coprocessor based on public key encryption algorithm |
CN110046622A (en) * | 2019-04-04 | 2019-07-23 | 广州大学 | A kind of attack sample generating method, device, equipment and storage medium having target |
CN110070115A (en) * | 2019-04-04 | 2019-07-30 | 广州大学 | A kind of single pixel attack sample generating method, device, equipment and storage medium |
CN110263674A (en) * | 2019-05-31 | 2019-09-20 | 武汉大学 | A kind of counterreconnaissance camouflage " contact clothing " generation method towards depth pedestrian weight identifying system |
CN111274601A (en) * | 2020-03-23 | 2020-06-12 | 上海金桥信息股份有限公司 | Image security identification system and method under network environment |
WO2021184976A1 (en) * | 2020-03-19 | 2021-09-23 | 支付宝(杭州)信息技术有限公司 | User characteristics extraction system and device for privacy protection |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101957911A (en) * | 2010-09-29 | 2011-01-26 | 汉王科技股份有限公司 | Face identification method and system |
CN105488486A (en) * | 2015-12-07 | 2016-04-13 | 清华大学 | Face recognition method and device for preventing photo attack |
CN106778525A (en) * | 2016-11-25 | 2017-05-31 | 北京旷视科技有限公司 | Identity identifying method and device |
US20170214701A1 (en) * | 2016-01-24 | 2017-07-27 | Syed Kamran Hasan | Computer security based on artificial intelligence |
-
2018
- 2018-03-19 CN CN201810223172.3A patent/CN108491785B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101957911A (en) * | 2010-09-29 | 2011-01-26 | 汉王科技股份有限公司 | Face identification method and system |
CN105488486A (en) * | 2015-12-07 | 2016-04-13 | 清华大学 | Face recognition method and device for preventing photo attack |
US20170214701A1 (en) * | 2016-01-24 | 2017-07-27 | Syed Kamran Hasan | Computer security based on artificial intelligence |
CN106778525A (en) * | 2016-11-25 | 2017-05-31 | 北京旷视科技有限公司 | Identity identifying method and device |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109271137A (en) * | 2018-09-11 | 2019-01-25 | 网御安全技术(深圳)有限公司 | A kind of modular multiplication device and coprocessor based on public key encryption algorithm |
CN109271137B (en) * | 2018-09-11 | 2020-06-02 | 网御安全技术(深圳)有限公司 | Modular multiplication device based on public key encryption algorithm and coprocessor |
CN110046622A (en) * | 2019-04-04 | 2019-07-23 | 广州大学 | A kind of attack sample generating method, device, equipment and storage medium having target |
CN110070115A (en) * | 2019-04-04 | 2019-07-30 | 广州大学 | A kind of single pixel attack sample generating method, device, equipment and storage medium |
CN110046622B (en) * | 2019-04-04 | 2021-09-03 | 广州大学 | Targeted attack sample generation method, device, equipment and storage medium |
CN110263674A (en) * | 2019-05-31 | 2019-09-20 | 武汉大学 | A kind of counterreconnaissance camouflage " contact clothing " generation method towards depth pedestrian weight identifying system |
CN110263674B (en) * | 2019-05-31 | 2022-02-15 | 武汉大学 | Anti-reconnaissance camouflage 'invisible clothes' generation method for deep pedestrian re-identification system |
WO2021184976A1 (en) * | 2020-03-19 | 2021-09-23 | 支付宝(杭州)信息技术有限公司 | User characteristics extraction system and device for privacy protection |
CN111274601A (en) * | 2020-03-23 | 2020-06-12 | 上海金桥信息股份有限公司 | Image security identification system and method under network environment |
Also Published As
Publication number | Publication date |
---|---|
CN108491785B (en) | 2020-07-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108491785A (en) | A kind of artificial intelligence image identification attack defending system | |
WO2020224122A1 (en) | Video monitoring method and apparatus, computer device, and storage medium | |
WO2021022717A1 (en) | Method and apparatus for analyzing feature correlation in federated learning, and readable storage medium | |
CN110661680A (en) | Method and system for detecting data stream white list based on regular expression | |
CN111049786A (en) | Network attack detection method, device, equipment and storage medium | |
CN111245783A (en) | Isolated environment data transmission device and method based on digital encryption technology | |
CN116132989B (en) | Industrial Internet security situation awareness system and method | |
CN112907321A (en) | Big data-based information security anomaly sensing platform for data mining and analysis | |
CN112561770A (en) | Confrontation sample defense method based on fragile watermark | |
Wandji et al. | Detection of copy-move forgery in digital images based on DCT | |
CN113139428A (en) | Target identification method, edge device, frontier defense monitoring system and readable storage medium | |
CN108512651A (en) | A kind of artificial intelligence image identification attack defense method, system and storage medium | |
CN110636077A (en) | Network security protection system and method based on unified platform | |
CN113839925A (en) | IPv6 network intrusion detection method and system based on data mining technology | |
CN108600168A (en) | A kind of secure coding method and system for the attack of artificial intelligence image identification | |
CN116756750A (en) | Medical sensitive data acquisition desensitization method | |
CN111209566A (en) | Intelligent anti-crawler system and method for multi-layer threat interception | |
CN115424350A (en) | Method for identifying violation behavior, computer device and computer readable storage medium | |
US11688200B2 (en) | Joint facial feature extraction and facial image quality estimation using a deep neural network (DNN) trained with a custom-labeled training dataset and having a common DNN backbone | |
CN115134080A (en) | Data transmission method and device based on security encryption chip | |
CN114117428A (en) | Method and device for generating detection model | |
CN110569646B (en) | File recognition method and medium | |
Maslan et al. | DDoS detection on network protocol using cosine similarity and N-Gram+ Method | |
CN117240598B (en) | Attack detection method, attack detection device, terminal equipment and storage medium | |
CN117149590B (en) | Data center system with data security monitoring module and monitoring method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |